arxiv:2509.25455
🔄 In a Training Loop
Alexander Kovrigin
waleko
AI & ML interests
AI for Code
Recent Activity
updated a model 1 day ago
waleko/Qwen2.5-Math-1.5B-RoPE-300k published a model 1 day ago
waleko/Qwen2.5-Math-1.5B-RoPE-300k updated a dataset 3 days ago
waleko/openmath-reasoning-cot-sftOrganizations
models 17
waleko/Qwen2.5-Math-1.5B-RoPE-300k
2B • Updated
waleko/Qwen3-8B-SFT-envbench_gpt5-yellow-green
Text Generation • 8B • Updated • 6
waleko/Qwen3-8B-SFT-envbench_qwen-all
Text Generation • 8B • Updated • 4
waleko/Qwen3-8B-SFT-envbench_qwen-green-yellow
Text Generation • 8B • Updated • 4
waleko/Qwen2.5-7B-Instruct-SFT-envbench_weave_2500
Text Generation • 8B • Updated • 3
waleko/Meta-Llama-3-8B-Instruct-SFT-envbench_weave_2500
Text Generation • 8B • Updated • 4
waleko/Llama-3.1-8B-Instruct-SFT-envbench_weave_2500
Text Generation • 8B • Updated • 4
waleko/Llama-3.1-8B-SFT-envbench_weave_2500
Text Generation • 8B • Updated • 3
waleko/Ministral-8B-Instruct-2410-SFT-envbench_weave_2500
Text Generation • 8B • Updated • 3
waleko/Qwen3-4B-SFT-envbench_weave_2500
Text Generation • 4B • Updated • 10
datasets 7
waleko/openmath-reasoning-cot-sft
Viewer • Updated • 502k • 86
waleko/deepscaler-sft-qwen25math-4k
Viewer • Updated • 15k • 32
waleko/piper-sharegpt
Viewer • Updated • 3.17k • 22
waleko/Dolci-RL-Zero-Math-7B-solved
Viewer • Updated • 2.05k • 7
waleko/TikZ-short-code
Viewer • Updated • 3.02k • 28 • 2
waleko/SWE-bench-traceback
Viewer • Updated • 1.85k • 64 • 1
waleko/unarXive-en2ru
Viewer • Updated • 10.4k • 24 • 3